afrideva
/

Echo-3B-GGUF

Text Generation

Model card Files Files and versions Community

Edit model card

euclaise/Echo-3B-GGUF

Quantized GGUF model files for Echo-3B from euclaise

Name	Quant method	Size
echo-3b.fp16.gguf	fp16	5.59 GB
echo-3b.q2_k.gguf	q2_k	1.20 GB
echo-3b.q3_k_m.gguf	q3_k_m	1.39 GB
echo-3b.q4_k_m.gguf	q4_k_m	1.71 GB
echo-3b.q5_k_m.gguf	q5_k_m	1.99 GB
echo-3b.q6_k.gguf	q6_k	2.30 GB
echo-3b.q8_0.gguf	q8_0	2.97 GB

Original Model Card:

Downloads last month: 250

GGUF

Model size

2.8B params

Architecture

stablelm

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples

Text Generation

Inference API (serverless) has been turned off for this model.

Model tree for afrideva/Echo-3B-GGUF

Base model

euclaise/Echo-3B

Quantized

(1)

this model

Datasets used to train afrideva/Echo-3B-GGUF